Feature selection for classification applications in neural network pruning

• Main Author: Gong, Rui
• Other Authors: Mao Kezhi
• Format: Thesis-Master by Coursework
• Language: English
• Published: Nanyang Technological University 2024
• Subjects: Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
• Online Access: https://hdl.handle.net/10356/172919
• Institution: Nanyang Technological University

The feature selection problem, which is a traditional machine learning problem, share many similarities with neural network pruning problem. However, traditional feature selection techniques are less visited in neural network pruning. To bridge this gap, comprehensive literature reviews on both fields are conducted in this dissertation. Then the neural network pruning problem is formulated as a feature selection problems, and feature selection methods are introduced to prune neural networks. Experiments results show that feature selection methods are useful for neural network pruning.